© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108583
    Prev
    Next
    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    pto
    -0.28
    unger
    -0.26
    æį®æѤ
    -0.25
    åIJİéĿ¢
    -0.24
    .front
    -0.24
     sided
    -0.24
    rire
    -0.24
     upcoming
    -0.24
     Positioned
    -0.24
    åıĮåĪĽ
    -0.23
    POSITIVE LOGITS
    VS
    0.25
    ä¿¡çĶ¨
    0.24
    åIJĦæľī
    0.24
     rem
    0.24
    éĥ½å¾Ī
    0.24
    [:]↵
    0.24
    airo
    0.23
    Rem
    0.23
     Echo
    0.23
    TestFixture
    0.23
    Activations Density 3.354%

    No Known Activations